Episodes
Four years of tape. Every episode is checked claim by claim and playable.
129 episodes in 2025
🎙LATENT SPACE
22m [State of Research Funding] Beyond NSF, Slingshots, Open Frontiers — Andy Konwinski, Laude Institute
Databricks and Perplexity co-founder Andy Konwinski discusses the launch of the Laud Institute, detailing its mission to revitalize open-source AI research and empower academic founders thro…
8 statements 3 featured 1 assessments 1 contradicted
🎙LATENT SPACE
17m [State of Code Evals] After SWE-bench, Code Clash & SOTA Coding Benchmarks recap — John Yang
In this NeurIPS interview, SWE-bench co-creator John Yang reviews the current landscape of AI coding benchmarks, introduces the competitive long-horizon framework Code Clash, and discusses t…
9 statements 3 featured 2 assessments
🎙LATENT SPACE
21m [State of MechInterp] SAEs in Production, Circuit Tracing, AI4Science, "Pragmatic" Interp — Goodfire
In this NeurIPS interview, Goodfire's Jack and Mark discuss the state of mechanistic interpretability, demonstrating how sparse autoencoders, latent steering, and circuit tracing transition …
6 statements 3 featured 2 assessments
🎙LATENT SPACE
34m [State of AI Papers 2025] Fixing Research with Social Signals, OCR & Implementation — Team AlphaXiv
In this episode of the Latent Space podcast, the founders of AlphaXiv discuss transforming static academic papers into interactive, executable research artifacts while analyzing standout Neu…
0 statements
🎙LATENT SPACE
28m [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton
Researchers Kevin Wang, Ishan Gaur, Michał Zawalski, and Professor Benjamin Eysenbach discuss their NeurIPS Best Paper award-winning research that successfully trains 1000-layer networks in …
12 statements 3 featured 9 assessments
🎙LATENT SPACE
26m [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual
Nina Lopatina of Contextual AI examines the evolution of context engineering, detailing how instruction-following rerankers, Agentic RAG, operational agent constraints, and dynamic tool orch…
8 statements 2 featured 2 assessments
🎙LATENT SPACE
24m [State of Evals] LMArena's $1.7B Vision — Anastasios Angelopoulos, LMArena
In this interview, Arena co-founder Anastasios Angelopoulos discusses the platform's evolution from a Berkeley research initiative into a venture-backed evaluation leader, detailing its orga…
18 statements 5 featured 4 assessments
🎙LATENT SPACE
27m [State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI
OpenAI post-training researcher Josh McGrath explores the technical evolution from GPT-4.1 to GPT-5.1, detailing breakthroughs in reasoning models, RLVR data engineering, token efficiency, a…
11 statements 3 featured 3 assessments
🎙LATENT SPACE
45m [State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor
Former OpenAI reasoning researcher and Cursor engineer Ashvin Nair analyzes the evolution of reinforcement learning, the disconnect between competitive benchmarks and real-world automation, …
25 statements 7 featured 2 assessments 1 contradicted
🎙LATENT SPACE
28m [State of AI Startups] Memory/Learning, RL Envs & DBT-Fivetran — Sarah Catanzaro, Amplify
Amplify Partners General Partner Sarah Catanzaro explores the intersection of data infrastructure and artificial intelligence, offering critical insights on venture funding realities, emergi…
19 statements 5 featured 1 assessments
🎙LATENT SPACE
1h 39m One Year of MCP — with David Soria Parria and AAIF leads from OpenAI, Goose, Linux Foundation
In this special Latent Space episode, co-hosts Alessio Fanelli and Swyx celebrate the one-year anniversary of the Model Context Protocol (MCP) with co-creator David Soria Parra and host a hi…
45 statements 17 featured 8 assessments
🎙LATENT SPACE
37m Steve Yegge's Vibe Coding Manifesto: Why Claude Code Isn't It & What Comes After the IDE
Live from the AI Engineer Summit, veteran engineer Steve Yegge explains how vibe coding, multi-agent architectures, and disposable code are transforming software development and making tradi…
17 statements 4 featured 2 assessments 1 contradicted
🎙LATENT SPACE
27m ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
OpenAI engineers Brian Fioca and Bill Chen join Latent Space to unpack the design, training, and evaluation behind Codex Max and GPT-5 agents. They explain how long-horizon autonomy, agent p…
19 statements 5 featured 7 assessments
🎙LATENT SPACE
1h 15m SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow)
In this podcast episode, Meta FAIR researchers and Roboflow leadership discuss the release, architecture, and real-world impact of SAM 3, Meta's open-source vision foundation model for conce…
30 statements 8 featured 11 assessments
🎙LATENT SPACE
40m ⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security
AI red teamers Pliny the Liberator and John V join the Latent Space podcast to discuss universal jailbreaking techniques, the mechanics of multi-agent adversarial attacks, and the imperative…
14 statements 5 featured 1 assessments
🎙LATENT SPACE
1h 9m AI to AE's: Grit, Glean, and Kleiner Perkins' next Enterprise AI hit — Joubin Mirzadegan, Roadrunner
Kleiner Perkins partner and Roadrunner co-founder Joubin Mirzadegan joins Swyx to discuss the evolution of his podcast Grit, key playbooks for scaling enterprise sales teams, and how LLMs ar…
22 statements 8 featured 2 assessments 1 contradicted
🎙LATENT SPACE
1h 11m The Future of Email: Superhuman CTO on Your Inbox As the Real AI Agent (Not ChatGPT) — Loïc Houssier
Superhuman CTO Loïc Houssier discusses the engineering architecture behind AI-driven email, the paradigm shift toward multimodal voice interfaces, and how cross-application context powers th…
22 statements 7 featured 3 assessments
🎙LATENT SPACE
34m The Great Evals Debate — Ankur Goyal & Malte Ubl
In this episode of the Latent Space Lightning Pod, Swyx hosts Braintrust founder Ankur Goyal and Vercel CTO Malte Ubl to debate the transition from 'vibe coding' to robust evaluation methodo…
15 statements 4 featured 1 assessments 1 contradicted
🎙LATENT SPACE
1h 4m World Models & General Intuition: Khosla's largest bet since LLMs & OpenAI
In this extensive studio interview and live technical demonstration, General Intuition CEO Pim de Witte explains how the startup utilizes Medal.tv's 3.8-billion gameplay dataset to build act…
34 statements 13 featured 1 assessments
🎙LATENT SPACE
1h 0m After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
AI pioneers Fei-Fei Li and Justin Johnson discuss the founding of World Labs and their flagship 3D generative platform, Marble, exploring how the frontier of artificial intelligence is movin…
15 statements 4 featured 4 assessments 1 contradicted
🎙LATENT SPACE
49m ⚡️ Building the AI Hardware Engineer with Matthias Wagner, Co-founder of Flux
Matthias Wagner, co-founder and CEO of Flux AI, discusses building an AI-powered hardware engineer within a browser-based CAD platform, demonstrating how autonomous agents synthesize circuit…
17 statements 5 featured 2 assessments 1 contradicted
🎙LATENT SPACE
27m ⚡️ 10x AI Engineers with $1m Salaries — Alex Lieberman & Arman Hezarkhani, Tenex
In this interview, Swyx speaks with Tenex co-founders Alex Lieberman and Arman Hezarkhani about how their AI-first engineering consultancy leverages output-based compensation to reward 10x d…
7 statements 2 featured
🎙LATENT SPACE
1h 26m Anthropic, Glean & OpenRouter: How AI Moats Are Built with Deedy Das of Menlo Ventures
In this episode of the Latent Space podcast, Menlo Ventures partner Deedy Das joins hosts Alessio Fanelli and Swix to analyze enterprise AI moats, Anthropic's rapid commercial growth, and th…
24 statements 8 featured 7 assessments 1 contradicted
🎙LATENT SPACE
35m ⚡ Inside GitHub’s AI Revolution: Jared Palmer Reveals Agent HQ & The Future of Coding Agents
In this in-depth interview on Latent Space, GitHub Senior Vice President Jared Palmer discusses the launch of GitHub Agent HQ, sharing key technical insights into the evolution of coding age…
14 statements 6 featured 2 assessments
🎙LATENT SPACE
43m ⚡ Inside Google Labs: Building The Gemini Coding Agent — Jed Borovik, Jules + AIE CODE Preview
Google Labs engineer Jed Borovik discusses the architectural evolution, capabilities, and product vision of Jules, Google's autonomous coding agent, while exploring how AI is reshaping devel…
9 statements 3 featured 2 assessments
🎙LATENT SPACE
49m ⚡️ The State of AI Engineer Hiring: Cheating, AI Adoption,Junior Devs — Vivek Ravisankar, HackerRank
Vivek Ravisankar, CEO of HackerRank, explores the state of software engineering hiring in the AI era, examining macroeconomic employment trends, anti-cheating strategies, and the revival of …
21 statements 7 featured 1 assessments
🎙LATENT SPACE
35m Terminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
In this launch event and panel hosted by Latent Space, the creators unveil Terminal-Bench 2.0—a rigorously audited real-world benchmark for AI coding agents—alongside Harbor, a unified open-…
11 statements 4 featured 2 assessments
🎙LATENT SPACE
53m Priscilla Chan and Mark Zuckerberg: Frontier AI + Virtual Biology To Solve All Diseases
In this episode of the Latent Space podcast, Priscilla Chan and Mark Zuckerberg detail how the Chan Zuckerberg Initiative converges frontier AI models, high-throughput wet labs, and custom i…
24 statements 6 featured 3 assessments
🎙LATENT SPACE
1h 0m How Zyphra went all-in on AMD + Why Devs feel faster with AI but are slower — with Quentin Anthony
Quentin Anthony explores Zyphra's adoption of AMD MI300X hardware and hybrid Mamba-transformer architectures, providing deep technical insights into low-level GPU kernel optimization and emp…
25 statements 8 featured 6 assessments
🎙LATENT SPACE
27m ⚡️Automating Scientific Discovery - Jessica Rumbelow, Leap Labs
Dr. Jessica Rumbelow of Leap Labs joins Swyx to discuss the Discovery Engine, demonstrating how mechanistic AI interpretability transforms scientific research from manual hypothesis testing …
11 statements 2 featured 3 assessments
🎙LATENT SPACE
42m ⚡️ Ship AI recap: Agents, Workflows, and Python — w/ Vercel CTO Malte Ubl
In this episode of Latent Space, Vercel CTO Malte Ubl breaks down the key announcements from Vercel's Ship AI event, covering the Workflow Development Kit, AI SDK v6, autonomous DevOps agent…
17 statements 6 featured 2 assessments
🎙LATENT SPACE
1h 37m The Agents Economy Backbone - with Emily Glassberg Sands, Head of Data & AI at Stripe
Emily Glassberg Sands, Head of Data and AI at Stripe, discusses the foundational infrastructure powering the emerging AI and agentic economy, spanning open commerce protocols, real-time foun…
35 statements 11 featured 9 assessments
🎙LATENT SPACE
43m Breaking AI to Fix It: Ian Webster's Journey from Discord's Clyde to Promptfoo's $18M Series A
In this interview, Promptfoo creator Ian Webster discusses the evolution of AI application security, explaining how automated synthetic red teaming and shifting testing left into CI/CD pipel…
10 statements 4 featured
🎙LATENT SPACE
1h 3m ⚡ Open Model Pretraining Masterclass — Elie Bakouch, HuggingFace SmolLM 3, FineWeb, FinePDF
In this episode of the Latent Space Podcast, Hugging Face researcher Elie Bakouch delivers a comprehensive masterclass on open-source LLM pretraining. He covers end-to-end dataset curation, …
16 statements 4 featured 5 assessments 1 contradicted
🎙LATENT SPACE
35m Terminal-Bench: Pushing Claude Code, OpenAI Codex, Factory Droid, et al to the limits
Alex and Mike Merrill join hosts Alessio and Swix to discuss Terminal-Bench, an open-source framework evaluating autonomous AI agents on diverse command-line tasks. They explore the advantag…
11 statements 3 featured 3 assessments 1 contradicted
🎙LATENT SPACE
1h 8m Why RL Won — Kyle Corbitt, OpenPipe (acq. CoreWeave)
In this episode of Latent Space, OpenPipe co-founder Kyle Corbitt discusses the evolution of model adaptation from prompt distillation and LoRAs to task-specific reinforcement learning, culm…
24 statements 5 featured 2 assessments 1 contradicted
🎙LATENT SPACE
45m Building Jamba 3B: the tiny Hybrid Transformer State Space Reasoning Model - Barak Lenz, CTO of AI21
Barak Lenz, CTO of AI21 Labs, explores the architectural design of hybrid Transformer-Mamba models like Jamba 3B and the Maestro enterprise orchestration platform. He outlines how AI21 solve…
16 statements 6 featured 2 assessments 1 contradicted
🎙LATENT SPACE
44m DevDay 2025: Apps SDK, Agent Kit, MCP, Codex and why Prompting is More Important than Ever
Recorded live at OpenAI DevDay 2025, Latent Space hosts Swix and Alessio Fanelli interview OpenAI Platform leaders Sherwin Wu and Christina Huang about major developer announcements, includi…
19 statements 6 featured 8 assessments
🎙LATENT SPACE
45m ⚡️Traversal: Causal ML and Reinforcement Learning
Traversal co-founders Anish Agarwal and Raaz Dwivedi discuss how their startup combines causal machine learning, agentic reasoning, and statistical testing to automate root cause analysis an…
13 statements 4 featured
🎙LATENT SPACE
55m The antidote to AI fatigue — Answer.ai Solveit
Answer.AI co-founders Jeremy Howard, Eric Ries, and Jono Whitaker introduce Solveit, a human-in-the-loop computing environment designed to counter AI fatigue by enabling just-in-time softwar…
13 statements 4 featured
🎙LATENT SPACE
1h 1m Taste is your Moat (Dylan Field of Figma)
Figma CEO Dylan Field joins the Latent Space podcast to discuss Figma's AI evolution, asserting that as artificial intelligence commoditizes code and software generation, human taste, design…
20 statements 6 featured
🎙LATENT SPACE
29m ⚡️Raising $1.1b to build the fastest LLM Chips on Earth — Andrew Feldman, Cerebras
Cerebras CEO Andrew Feldman discusses the company's $1.1 billion fundraise and details how their specialized wafer-scale silicon overcomes memory bandwidth bottlenecks to power the next gene…
17 statements 5 featured 5 assessments 1 contradicted
🎙LATENT SPACE
26m ⚡️Claude Sonnet 4.5 and Anthropic's roadmap for Agents and Developers — Mike Krieger, Anthropic
Anthropic Chief Product Officer Mike Krieger discusses the launch of Claude Sonnet 4.5, detailing how Anthropic integrates design taste, bidirectional research-product feedback, and modular …
12 statements 4 featured
🎙LATENT SPACE
1h 21m Amp: The Emperor Has No Clothes
Quinn Slack and Thorsten Ball join the Latent Space podcast to discuss the inception, architecture, and high-velocity development of Amp, Sourcegraph's autonomous coding agent. They explore …
34 statements 10 featured
🎙LATENT SPACE
26m ⚡️Snowglobe: Simulations for your AI
In this episode of the Latent Space podcast, Guardrails AI creator Shreya Rajpal introduces Snowglobe, an end-to-end simulation engine designed to stress-test AI agents, chatbots, and enterp…
15 statements 5 featured 2 assessments
🎙LATENT SPACE
32m ⚡️ Beyond Transformers with Power Retention
In this episode of the Latent Space Podcast, Diego Bachman of Manifest AI discusses replacing transformer attention bottlenecks with Power Retention, an architecture utilizing fixed-size mem…
14 statements 4 featured 3 assessments 1 contradicted
🎙LATENT SPACE
35m ⚡️No, Don't Do Palantir for AI - Brendan Falk, Hercules (AUDIO FIXED)
Former Fig founder Brendan Falk reflects on his journey attempting to build an 'AI-native Palantir' with Zeus, breaking down the operational and economic challenges of enterprise AI consulti…
11 statements 4 featured 1 assessments 1 contradicted
🎙LATENT SPACE
1h 3m Context Engineering for Agents - Lance Martin, LangChain
In this episode of the Latent Space podcast, LangChain's Lance Martin explores the core principles of context engineering, detailing how developers can manage agent token flow, memory, retri…
22 statements 6 featured 8 assessments 1 contradicted
🎙LATENT SPACE
1h 4m A Technical History of Generative Media
Fal leadership Gorkem Yurtseven and Batuhan Taskaya discuss the evolution of their generative media platform into a $100M+ ARR business with podcast hosts Alessio and Swix. They explore low-…
21 statements 7 featured 1 assessments
🎙LATENT SPACE
33m ⚡️Launching Ona: Coding Agent with Fully Sandboxed Cloud Environment
Gitpod co-founders Johannes Landgraf and Chris Weichel join Latent Space to announce their company's pivot and rebrand to Ona, an agent-first cloud development platform. They showcase how fu…
15 statements 5 featured 1 assessments
🎙LATENT SPACE
1h 18m Better Data is All You Need — Ari Morcos, Datology
In this episode of the Latent Space podcast, Datology CEO Ari Morcos discusses why automated data curation is AI's most critical frontier, demonstrating how algorithmic filtering, synthetic …
50 statements 21 featured 7 assessments 1 contradicted
🎙LATENT SPACE
57m Long Live Context Engineering - with Jeff Huber of Chroma
In this episode of Latent Space, Chroma co-founder and CEO Jeff Huber explores the evolution of AI search infrastructure, introducing 'context engineering' to resolve context rot while advoc…
21 statements 9 featured 1 assessments
🎙LATENT SPACE
47m ⚡️Accelerators @ 3x NVIDIA H200 perf, Made in the USA - Thomas Sohmers + Mitesh Agrawal, Positron AI
Positron AI founders Thomas Sohmers and Mitesh Agrawal discuss how their memory-bandwidth-optimized hardware architecture accelerates transformer inference, featuring zero-step Hugging Face …
24 statements 7 featured 8 assessments 3 contradicted
🎙LATENT SPACE
1h 8m Greg Brockman on OpenAI's Road to AGI
OpenAI President Greg Brockman discusses the evolution of frontier reasoning models, the launch of GPT-5, and the emerging paradigms of autonomous agent orchestration. He explores the comput…
32 statements 10 featured 6 assessments 1 contradicted
🎙LATENT SPACE
1h 14m The AI Agenda: GPT5 leaks and the business of AI News — Steph Palazzolo, The Information
Stephanie Palazzolo, AI reporter at The Information, joins the Latent Space podcast to discuss the investigative craft of tech journalism, the unit economics of AI inference startups, and th…
18 statements 8 featured 6 assessments
🎙LATENT SPACE
37m ⚡️OpenCode: Claude Code but Open Source, with Any Model, and frontier TUI - with Dax Reed (@thdxr)
Dax Reed joins Latent Space to present OpenCode, an open-source, model-agnostic terminal coding assistant built with a full-screen TUI, modular architecture, and enduring developer ergonomic…
23 statements 5 featured 3 assessments
🎙LATENT SPACE
28m ⚡️Mercury: Ultra-Fast Diffusion LLMs — Estefano Ermon, CEO Inception Labs
Stanford professor and Inception Labs CEO Stefano Ermon discusses the breakthrough mechanics, ultra-fast inference capabilities, and systems architecture of discrete diffusion language model…
14 statements 5 featured 3 assessments
🎙LATENT SPACE
22m ⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra
Composio co-founders Karan Vaidya and Soham Ganatra join the Latent Space podcast to discuss building self-evolving agent skills, scaling tool maintenance autonomously, and leveraging advanc…
11 statements 3 featured 3 assessments
🎙LATENT SPACE
1h 18m The RLVR Revolution — with Nathan Lambert (AI2, Interconnects.ai)
In this episode, AI2 post-training researcher Nathan Lambert joins hosts Alessio Fanelli and Swix to break down the rise of Reinforcement Learning from Verifiable Rewards (RLVR), the mechani…
40 statements 11 featured 8 assessments
🎙LATENT SPACE
26m ⚡️Using RFT to Build Clinical Superintelligence
In this episode of the Latent Space Lightning Pod, Ambience engineering leader Brendan Fortuna discusses how advanced Reinforcement Fine-Tuning (RFT), robust evaluation pipelines, and deep c…
19 statements 6 featured 4 assessments
🎙LATENT SPACE
3h 53m 🕰️ The Oral History of Windsurf (ft. Varun Mohan, Scott Wu, Jeff Wang, Kevin Hou, Anshul R)
This comprehensive retrospective presents the oral history of Windsurf and Cognition AI, charting the evolution of AI developer tooling from low-level GPU infrastructure and code autocomplet…
104 statements 27 featured 13 assessments 4 contradicted
🎙LATENT SPACE
33m ⚡️Math Olympiad gold medalist explains OpenAI and Google DeepMind IMO Gold Performances
Former Math Olympiad gold medalist Dr. Jasper Zhang joins Latent Space to analyze how Google DeepMind and OpenAI achieved historic IMO gold performances using natural language reasoning. He …
15 statements 4 featured 4 assessments 1 contradicted
🎙LATENT SPACE
56m AI is Eating Search
In this episode of the Latent Space Podcast, Scrunch.ai co-founder Robert joins Alessio and Swix to break down the mechanics of AI search engines, the transition from traditional SEO to Agen…
25 statements 7 featured 5 assessments
🎙LATENT SPACE
39m ⚡️ARC-AGI-3: The Interactive Reasoning Benchmark
Greg Kamradt from the ARC Prize Foundation joins the Latent Space Lightning Pod to announce ARC-AGI-3, an interactive reasoning benchmark comprising 100 novel 2D game environments designed t…
24 statements 10 featured 6 assessments 1 contradicted
🎙LATENT SPACE
28m ⚡️The Future of Notebooks - with Akshay Agrawal of Marimo
In this Latent Space Lightning episode, Marimo creator Akshay Agrawal discusses how Marimo reinvents computational notebooks for AI through reactive execution, pure Python files, and interac…
9 statements 3 featured 7 assessments
🎙LATENT SPACE
1h 15m Cline: The Collaborative AI Coder
In this podcast episode, Cline creators Saoud Rizwan and Pash explore the architecture, open-source strategy, and context engineering principles powering their AI coding agent. They detail h…
16 statements 3 featured 2 assessments 1 contradicted
🎙LATENT SPACE
34m ⚡️Ranking Agentic LLMs — Pratik Bhavsar, Galileo
In this episode of the Latent Space Lightning Pod, hosts Swyx and Alessio Fanelli interview Pratik Bhavsar of Galileo Labs to explore the methodologies, surprising model rankings, and future…
12 statements 4 featured 5 assessments 2 contradicted
🎙LATENT SPACE
1h 4m Personalized AI Language Education — with Andrew Hsu, Speak
Speak co-founder and CTO Andrew Hsu joins Latent Space to discuss building an AI-native language tutor, covering Speak's custom speech infrastructure, Korean market breakout, pedagogical met…
40 statements 13 featured 2 assessments
🎙LATENT SPACE
49m AI Video Is Eating The World — Olivia and Justine Moore, a16z
In this episode of the Latent Space podcast, a16z investment partners Justine and Olivia Moore explore the explosive rise of AI video, dissecting viral social media phenomena, creator econom…
16 statements 5 featured 5 assessments
🎙LATENT SPACE
27m ⚡️Anthropic vs Cognition on Multi-Agents: A Breakdown with Dylan Davis
Swix and Dylan Davis break down the competing AI agent philosophies of Anthropic and Cognition, comparing multi-agent parallel research architectures with single-agent sequential coding syst…
9 statements 3 featured 4 assessments
🎙LATENT SPACE
1h 18m Information Theory for Language Models: Jack Morris
Cornell Tech PhD researcher Jack Morris joins swyx to unpack the information-theoretic foundations of language models, exploring vector embedding privacy, empirical parameter storage limits,…
23 statements 6 featured 7 assessments 1 contradicted
🎙LATENT SPACE
52m ⚡️Warp 2.0: the Agentic Development Environment - Zach Lloyd and Ben Holmes
Warp CEO Zach Lloyd and Ben Holmes join the Latent Space podcast to launch Warp 2.0, showcasing its transformation from an AI-native terminal into an Agentic Development Environment with mul…
30 statements 10 featured 5 assessments
🎙LATENT SPACE
1h 17m Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
OpenAI researcher Noam Brown joins the Latent Space Podcast to discuss the evolution of test-time reasoning models like o1 and o3, lessons from game-theoretic breakthroughs like Cicero and L…
30 statements 7 featured 4 assessments
🎙LATENT SPACE
1h 18m The Shape of Compute (Chris Lattner of Modular)
In this in-depth discussion, Modular founder and CEO Chris Lattner joins Alessio Fanelli and Shawn 'swyx' Wang to explore the architecture of Mojo and MAX, the shifting economics of AI infer…
23 statements 6 featured 5 assessments
🎙LATENT SPACE
34m ⚡️Launching AI Diplomacy: the hardest LLM Game Benchmark yet - Alex Duffy
Alex Duffy, Head of AI at Every, breaks down the creation and strategic insights of the AI Diplomacy game benchmark while discussing Every's multidisciplinary culture, practical AI tooling, …
12 statements 3 featured 3 assessments
🎙LATENT SPACE
28m Quadratic: The AI Spreadsheet
Quadratic founder and CEO David Kirkos joins the Latent Space podcast to demonstrate how combining WebAssembly, polyglot code execution (SQL, Python, and JavaScript), and AI agents transform…
15 statements 5 featured 3 assessments
🎙LATENT SPACE
1h 53m The Utility of Interpretability — Emmanuel Amiesen
Anthropic research scientist Emmanuel Ameisen discusses the open-source release of circuit tracing tools for Gemma 2B, demonstrating how sparse autoencoders and attribution graphs expose int…
31 statements 8 featured 13 assessments 1 contradicted
🎙LATENT SPACE
27m [AIEWF Preview] Containing Agent Chaos — Solomon Hykes
Docker creator and Dagger founder Solomon Hykes discusses the evolving role of platform engineering in the age of AI coding agents, advocating for open, modular container environments that d…
9 statements 3 featured 1 assessments
🎙LATENT SPACE
24m [AIEWF Preview] Gemini in 2025 and Realtime Voice AI
Recorded on-site at Google I/O, hosts from TWIML AI and Latent Space interview Google DeepMind product leaders and Daily's CEO to examine recent Gemini platform upgrades, infrastructure trad…
19 statements 6 featured 7 assessments 1 contradicted
🎙LATENT SPACE
20m [AIEWF Preview] CloudChef: Your Robot Chef - Michellin-Star food at $12/hr (w/ Kitchen tour!)
CloudChef founder Nikhil joins hosts Sean and Vibu Sabra to discuss how their software-first robotics platform and $12-per-hour labor model automate commercial kitchens, followed by a walkth…
10 statements 3 featured 3 assessments
🎙LATENT SPACE
59m The AI Coding Factory
Factory AI co-founders Matan Grinberg and Eno Reyes join the Latent Space podcast to discuss their autonomous software engineering platform, detailing how autonomous Droids, first-principles…
26 statements 12 featured
🎙LATENT SPACE
38m ⚡️Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime Intellect
In this Latent Space podcast episode, Will Brown of Prime Intellect joins Alessio and Wix to analyze the Claude 4 release, examine the mechanics of extended thinking and reward hacking, and …
17 statements 4 featured 1 assessments
🎙LATENT SPACE
32m DeepWiki: The GitHub Encyclopedia
Silas Alberti of Cognition joins the Latent Space podcast to discuss DeepWiki, an AI-powered documentation and deep research tool that generates high-level architectural knowledge graphs for…
17 statements 5 featured 2 assessments
🎙LATENT SPACE
53m ChatGPT Codex: The Missing Manual
OpenAI engineers Josh and Alexander join the Latent Space Podcast to detail the architecture, developer best practices, and design philosophy behind ChatGPT Codex. They discuss shifting from…
15 statements 5 featured 1 assessments
🎙LATENT SPACE
17m ⚡️Open Questions in Agentic RL — Will Brown (Prime Intellect)
Will Brown from Prime Intellect presents a comprehensive technical roadmap for the open-source community to train frontier agentic reinforcement learning models capable of long-horizon auton…
15 statements 8 featured 2 assessments 1 contradicted
🎙LATENT SPACE
1h 16m Claude Code: Anthropic's CLI Agent
In this Latent Space episode, Anthropic's Kat Wu and Boris Cherny discuss Claude Code, exploring its minimalist terminal architecture, internal dogfooding genesis, economic return on enginee…
44 statements 15 featured 5 assessments
🎙LATENT SPACE
35m Zed Agents — with Zed Cofounders Nathan Sobo & Antonio Scandurra
Zed co-founders Nathan Sobo and Antonio Scandurra discuss the native Rust architecture behind their GPU-accelerated code editor, demonstrating its new autonomous AI agents, Model Context Pro…
16 statements 10 featured 5 assessments
🎙LATENT SPACE
20m Voice AI Masterclass — Kwindla Hultman Kramer and swyx
In this Latent Space episode, Shawn Wang (swyx) and Daily CEO Kwindla Hultman Kramer announce the Voice AI Masterclass, exploring the core architectural pillars, open-source orchestration to…
11 statements 4 featured 3 assessments
🎙LATENT SPACE
15m What is an RL environment? w/ Nous Research's Roger Jin
In this technical presentation, Roger Jin of Nous Research explains why reinforcement learning is essential for next-generation language models and introduces an open-source, microservice-ba…
9 statements 2 featured
🎙LATENT SPACE
30m ⚡️Factorio Learning Environment: the ultimate Game Agent Eval — Jack Hopkins
Researchers Jack Hopkins and Marc introduce the Factorio Learning Environment (FLE), a high-complexity AI benchmark that evaluates large language models on spatial reasoning, hierarchical pl…
8 statements 3 featured 6 assessments 1 contradicted
🎙LATENT SPACE
1h 6m Why Every Agent needs Open Source Cloud Sandboxes
E2B co-founder Vasek Mlejnsky joins hosts Alessio Fanelli and Swix to discuss the architecture, scaling challenges, and strategic vision behind building open-source cloud sandboxes designed …
25 statements 6 featured 4 assessments
🎙LATENT SPACE
42m Tiny Teams: $6m ARR, 5m users with 4 employees — Sid Bendre, Oleve (Quizard AI/Unstuck AI)
Sid Bendre, co-founder and CTO of Oleve, explains how a lean four-person team built and scaled multiple viral consumer AI applications to 5 million users and $6 million in ARR using determin…
16 statements 6 featured 1 assessments
🎙LATENT SPACE
34m Sleep-Time Compute — Letta AI (Charles Packer, Charlie Snell, Kevin Lin)
In this Latent Space podcast episode, Letta AI researchers Charles Packer, Kevin Lin, and Charlie Snell introduce 'Sleep-Time Compute,' a post-training paradigm that utilizes idle GPU time t…
15 statements 5 featured 4 assessments
🎙LATENT SPACE
27m The Rise and Fall of the Vector DB category: Jo Kristian Bergum (ex-Chief Scientist, Vespa)
Former Vespa Chief Scientist Jo Kristian Bergum analyzes why the standalone vector database category is declining and shares practical guidance on building resilient, hybrid search architect…
8 statements 2 featured
🎙LATENT SPACE
45m GPT 4.1: The New OpenAI Workhorse
OpenAI researchers Michelle Pokrass and Josh join the Latent Space podcast to detail the GPT-4.1 model family, highlighting advances in post-training, software engineering, one-million-token…
24 statements 7 featured 6 assessments
🎙LATENT SPACE
1h 12m SF Compute: Commoditizing Compute
In this interview, SF Compute founder Evan Conrad explores the shifting economics of GPU infrastructure, explaining how the unbundling of hardware from software, bare-metal auditing, and fin…
25 statements 7 featured 3 assessments 1 contradicted
🎙LATENT SPACE
1h 14m Claude Plays Pokémon Hackathon: Escape from Mt. Moon!
This hackathon kickoff event explores the development, engineering challenges, and cloud infrastructure behind autonomous AI agents playing Pokémon, featuring technical talks from Anthropic,…
11 statements 3 featured
🎙LATENT SPACE
1h 20m The Creators of Model Context Protocol
In this episode of the Latent Space podcast, Anthropic engineers Justin and David discuss the origins, core architecture, and open-source ecosystem of the Model Context Protocol (MCP), expla…
0 statements
🎙LATENT SPACE
31m The #1 SWE-Bench Verified Agent
Augment Code leader Guy Gur-Ari joins the Latent Space podcast to discuss their top-ranked SWE-bench Verified agent, breaking down the architecture, evaluation pipelines, and enterprise phil…
17 statements 8 featured 4 assessments
🎙LATENT SPACE
1h 42m The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot
HubSpot CTO and Agent.ai founder Dharmesh Shah joins Swyx and Alessio Fanelli to discuss the technical architecture of multi-agent networks, open protocols like MCP, pragmatic software engin…
35 statements 12 featured 1 assessments
🎙LATENT SPACE
48m Building Manus AI (first ever Manus Meetup)
At the first Manus meetup, the product lead presents the technical architecture, product history, and generalist philosophy behind Manus, an autonomous AI agent running in isolated cloud vir…
0 statements
🎙LATENT SPACE
46m The Magic of LLM Distillation — Rishabh Agarwal, Google DeepMind
Google DeepMind Staff Research Scientist Rishabh Agarwal joins the Latent Space podcast to break down the technical resurgence of LLM distillation, detailing how logit-based matching, on-pol…
24 statements 7 featured 6 assessments
🎙LATENT SPACE
31m Fullstack-Bench: The Eval for Coding Agents — with Sujay Jayakar, Chief Scientist, Convex
In this episode of Latent Space, Convex Co-founder and Chief Scientist Sujay Jayakar introduces Fullstack-Bench, a comprehensive benchmark evaluating AI coding agents across different backen…
11 statements 4 featured 3 assessments
🎙LATENT SPACE
35m npm install Agents — with Sunil Pai and Rita Kozlov (VP AI) of Cloudflare
Cloudflare's Rita Kozlov and Sunil Pai join Sean Wang to introduce Cloudflare Agents, exploring how Durable Objects provide a persistent, actor-model foundation for running stateful, autonom…
18 statements 6 featured 2 assessments 1 contradicted
🎙LATENT SPACE
1h 17m Snipd: The AI Podcast App for Learning — with CEO Kevin Ben-Smith
Shawn 'Swix' Wang interviews Snipd CEO and co-founder Kevin Ben-Smith to explore how their AI-first podcast player is engineered to transform passive spoken audio into structured, retrievabl…
26 statements 8 featured 7 assessments 1 contradicted
🎙LATENT SPACE
27m [Lightning Pod] Evals: How to Improve AI Consistently — with Hamel Husain and Shreya Shankar
Hamel Husain and Shreya Shankar break down the essentials of AI evaluations, explaining how systematic measurement, grounded synthetic data, domain-calibrated LLM judges, and practical data …
13 statements 4 featured
🎙LATENT SPACE
25m The new OpenAI Agents Platform: CUA, Web Search, Responses API, Agents SDK!!
OpenAI team members Romain Huet and Nikunj Handa join the Latent Space podcast to introduce their major agent platform releases, including the Responses API, Agents SDK, Web Search, File Sea…
14 statements 5 featured 4 assessments
🎙LATENT SPACE
28m Solve coding, solve AGI [Reflection.ai launch w/ CEO Misha Laskin]
Reflection AI co-founder and CEO Misha Laskin discusses the company's emergence from stealth to build fully autonomous coding agents powered by the convergence of large language models and r…
16 statements 6 featured
🎙LATENT SPACE
37m How Claude Plays Pokémon was made
Anthropic engineer David Hershey joins Latent Space to detail how he built 'Claude Plays Pokémon,' examining agent architecture, spatial reasoning hurdles, context window management, and the…
16 statements 5 featured 2 assessments
🎙LATENT SPACE
1h 1m Browserbase: Browser Infrastructure For Your AI Agents
In this episode of the Latent Space podcast, Browserbase founder Paul Klein discusses building dedicated headless cloud browser infrastructure to power autonomous AI web agents. He explores …
37 statements 11 featured 3 assessments
🎙LATENT SPACE
28m Gemini 2.0 Flash and Flash Thinking: the new SOTA models for the agentic era
Google AI Studio Product Lead Logan Kilpatrick joins hosts Alessio and Swix to break down the Gemini 2.0 ecosystem, detailing reasoning scaling in Flash Thinking, real-time multimodal APIs, …
10 statements 2 featured 2 assessments
🎙LATENT SPACE
20m Raycast: Your AI Automation Assistant
Raycast CEO Thomas Paul Mann joins the Latent Space podcast to discuss the launch of AI Extensions, explaining how the platform leverages model distillation, TypeScript developer tooling, an…
13 statements 4 featured 2 assessments
🎙LATENT SPACE
17m S1: the $6 DeepSeek R1 Competitor (ft. Entropix)
Hosts Swix and Alessio interview engineer and writer Tim to unpack the breakthroughs behind the S1 reasoning model and Entropix dynamic sampling framework. The discussion explores data-effic…
0 statements
🎙LATENT SPACE
1h 0m Why is everyone cloning Deep Research?
Google Deep Research creators Arush Sehgal and Mukund Sridhar join the Latent Space podcast to unpack the architecture, user experience design, and engineering innovations behind autonomous …
27 statements 6 featured 3 assessments
🎙LATENT SPACE
1h 7m Bee AI: The Wearable Ambient Agent
Bee co-founders Maria and Ethan join the Latent Space Podcast to discuss the hardware engineering, memory architecture, and autonomous agent capabilities powering their ambient wearable AI d…
22 statements 9 featured 3 assessments
🎙LATENT SPACE
22m smol agents are all you need
Hugging Face's Aymeric joins the Lightning Pod to discuss smolagents and the power of code-first agent architectures over standard JSON tool calling. The episode explores agent evaluation on…
8 statements 3 featured 2 assessments
🎙LATENT SPACE
1h 35m The AI Architect: Bret Taylor
In this in-depth interview on the Latent Space podcast, veteran technologist and OpenAI Chairman Bret Taylor discusses the evolution of software engineering, the architectural blueprint for …
23 statements 7 featured 2 assessments 1 contradicted
🎙LATENT SPACE
1h 2m Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire
In this episode, Pydantic founder Samuel Colvin joins Alessio Fanelli and Swix to explore Pydantic's expansion into artificial intelligence, detailing Pydantic AI's type-safe agent graph arc…
21 statements 6 featured 4 assessments
🎙LATENT SPACE
31m Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO)
Portkey.ai CEO Rohit Agarwal joins hosts Swix and Alessio to discuss the critical role of AI gateways in managing model routing, production guardrails, OpenTelemetry observability, and multi…
15 statements 3 featured 1 assessments
🎙LATENT SPACE
1h 6m The Agent Reasoning Interface: Claude, ChatGPT Canvas, Tasks, Operator — with Karina Nguyen, OpenAI
In this episode of the Latent Space podcast, OpenAI research lead Karina Nguyen explains how post-training, behavioral design, and synthetic data power interactive interfaces like ChatGPT Ca…
30 statements 8 featured 2 assessments
🎙LATENT SPACE
34m Beating OpenAI and Anthropic by Looking At Data: the new #1 on SWE-Bench w/ W&B CTO Shawn Lewis
Weights & Biases CTO Shawn Lewis joins the Latent Space Podcast to detail how he achieved a record 64.6% solve rate on the SWE-bench Verified leaderboard using OpenAI's o1 model, the Phase S…
13 statements 4 featured 2 assessments
🎙LATENT SPACE
1h 13m Outlasting Noam Shazeer, Crowdsourcing Chai AI w/ 1.4m DAU — with William Beauchamp, Chai Research
Chai AI founder and CEO William Beauchamp discusses scaling an AI entertainment platform to 1.4 million daily active users through crowdsourced model training, high-efficiency inference arch…
35 statements 12 featured 3 assessments
🎙LATENT SPACE
23m The Unreasonable Effectiveness of Reasoning Distillation: using DeepSeek R1 to beat OpenAI o1
In this Latent Space Podcast episode, the Bespoke Labs team discusses their 48-hour sprint distilling DeepSeek-R1 into Qwen, demonstrating how open reasoning traces, streamlined data curatio…
3 statements 1 featured 2 assessments
🎙LATENT SPACE
57m DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)
In this episode of the Latent Space podcast, Baseten leaders Amir and Yining Zhang explore the architectural breakthroughs of DeepSeek V3 and the technical evolution of the SGLang inference …
18 statements 6 featured 10 assessments 1 contradicted
🎙LATENT SPACE
31m OpenAI o1 isn’t a chat model (and that’s the point)
In this episode of the Latent Space podcast, hosts and AI practitioners deconstruct OpenAI's o1 reasoning model, explaining why it requires a departure from conversational chat in favor of s…
20 statements 6 featured
🎙LATENT SPACE
55m Beating Google at Search with Neural PageRank and $5M of H200s — with Will Bryk of Exa.ai
Exa.ai CEO Will Bryk discusses rebuilding web search from first principles using neural link-prediction foundation models, explaining how variable compute, agentic workflows, and specialized…
21 statements 8 featured 1 assessments
🎙LATENT SPACE
52m AI Engineering for Art - with comfyanonymous
In this episode of the Latent Space Podcast, hosts Alessio Fanelli and Swix interview Comfyanonymous, the creator of ComfyUI, exploring the technical architecture, memory management optimiza…
22 statements 9 featured 4 assessments
🎙LATENT SPACE
16m The State of Reasoning — from Nathan Lambert, Interconnects/AI2 [LS Live @ NeurIPS 2024]
In this NeurIPS 2024 presentation, Nathan Lambert explores the state of artificial intelligence reasoning, examining how chain-of-thought prompting, verifiable post-training reinforcement le…
11 statements 4 featured 2 assessments
🎙LATENT SPACE
1h 51m 2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
In their milestone 100th episode, Latent Space co-hosts Alessio Fanelli and Swyx deliver a comprehensive 2024 retrospective analyzing the rise of AI engineering, test-time reasoning compute,…
29 statements 9 featured 12 assessments 1 contradicted